Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to hierarchical structures or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rir
    -0.17
     Dag
    -0.16
    abb
    -0.16
    anko
    -0.16
    .dispatchEvent
    -0.15
     panc
    -0.14
    inke
    -0.14
    annes
    -0.14
    loy
    -0.14
    ysa
    -0.14
    POSITIVE LOGITS
     ones
    0.21
     Ones
    0.16
    izedName
    0.16
    .ribbon
    0.15
    ëħ
    0.14
    ary
    0.14
    chine
    0.14
    dech
    0.14
    084
    0.14
     counterparts
    0.14
    Act Density 0.360%

    No Known Activations